CN112711748B - Finger vein identity authentication method and device, electronic equipment and storage medium - Google Patents
Finger vein identity authentication method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112711748B CN112711748B CN202110053733.1A CN202110053733A CN112711748B CN 112711748 B CN112711748 B CN 112711748B CN 202110053733 A CN202110053733 A CN 202110053733A CN 112711748 B CN112711748 B CN 112711748B
- Authority
- CN
- China
- Prior art keywords
- similarity
- radon
- identity
- feature
- finger vein
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 210000003462 vein Anatomy 0.000 title claims abstract description 101
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000000605 extraction Methods 0.000 claims description 30
- 229910052704 radon Inorganic materials 0.000 claims description 17
- SYUHGPGVQRZVTB-UHFFFAOYSA-N radon atom Chemical compound [Rn] SYUHGPGVQRZVTB-UHFFFAOYSA-N 0.000 claims description 17
- 238000010586 diagram Methods 0.000 claims description 16
- 238000012216 screening Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 abstract description 10
- 230000006870 function Effects 0.000 description 20
- 239000000523 sample Substances 0.000 description 18
- 238000004422 calculation algorithm Methods 0.000 description 13
- 230000011218 segmentation Effects 0.000 description 13
- 235000020061 kirsch Nutrition 0.000 description 8
- 238000003708 edge detection Methods 0.000 description 6
- 238000006073 displacement reaction Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000003706 image smoothing Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 229920001690 polydopamine Polymers 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000009966 trimming Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/60—Static or dynamic means for assisting the user to position a body part for biometric acquisition
- G06V40/67—Static or dynamic means for assisting the user to position a body part for biometric acquisition by interactive indications to the user
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/14—Vascular patterns
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Security & Cryptography (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The application provides a finger vein identity authentication method, a device, electronic equipment and a storage medium, which are used for solving the problem that the false recognition rate of finger vein identity authentication on images acquired in a complex image acquisition environment is high. The method comprises the following steps: acquiring a finger vein image of an identity person to be authenticated; extracting a region of interest in the finger vein image; extracting a radon-class feature map in the region of interest; calculating the similarity between the radon-class feature images and a plurality of feature images in a feature template library to obtain a plurality of similarities; and determining the identity information of the identity personnel to be authenticated according to the multiple similarities. In the implementation process, the false recognition rate of finger vein identity authentication on images acquired in a complex image acquisition environment can be effectively reduced by using the radon-class feature map.
Description
Technical Field
The application relates to the technical field of image processing and image recognition, in particular to a finger vein identity authentication method, a finger vein identity authentication device, electronic equipment and a storage medium.
Background
Finger vein authentication (finger-vein personal identification), also known as finger vein verification (finger-vein verification) or finger vein recognition (finger-vein identification), is a new biometric technique that uses images of vein distribution within a finger to identify the finger. The finger vein identity authentication and the primary fingerprint identification are relatively close, and are authenticated and identified by means of image feature comparison.
At present, the idea of performing finger vein identity authentication through a finger vein image of a person is approximately that a pre-designed feature extraction algorithm is utilized to extract template features of a registered sample image, the feature extraction algorithm is utilized to extract features of an image to be verified, and finally, the finger vein identity authentication is performed according to a comparison result of the features of the image to be verified and the template features of the registered sample image. The feature extraction algorithm comprises the following steps: a cure-based algorithm (e.g., maxcurr and mean cure feature algorithms), a filter-based algorithm (e.g., gabor filter algorithm), and a local texture-based algorithm (e.g., local binary pattern algorithm). However, in practice, it has been found that images acquired in a complex image acquisition environment generally include different image backgrounds, image noise, finger displacement, rotation angles, and the like, and the feature extraction algorithms described above are relatively sensitive to information such as image backgrounds, image noise, finger displacement, rotation angles, and the like, and the false recognition rate (False Accept Rate, FAR) of finger vein identity authentication of images acquired in a complex image acquisition environment is high by using the feature extraction algorithms.
Disclosure of Invention
The embodiment of the application aims to provide a finger vein identity authentication method, a device, electronic equipment and a storage medium, which are used for solving the problem that the false recognition rate of finger vein identity authentication on images acquired in a complex image acquisition environment is high.
The embodiment of the application provides a finger vein identity authentication method, which comprises the following steps: acquiring a finger vein image of an identity person to be authenticated; extracting a region of interest in the finger vein image; extracting a radon-class feature map in the region of interest; calculating the similarity between the radon-class feature images and a plurality of feature images in a feature template library to obtain a plurality of similarities; and determining the identity information of the identity personnel to be authenticated according to the multiple similarities. In the implementation process, extracting a region of interest in the finger vein image, extracting a radon-class feature map in the region of interest, and then performing finger vein identity authentication by using the radon-class feature map; because the radon-class feature map allows the statistical information of the spatially distributed images (spatially distributed image) to be aggregated into compact feature descriptors (feature descriptors) and is insensitive to information such as image background, image noise, finger displacement, rotation angle and the like, the use of the radon-class feature map can effectively reduce the false recognition rate of finger vein identity authentication on images acquired in a complex image acquisition environment.
Optionally, in an embodiment of the present application, extracting a radon-class feature map in the region of interest includes: extracting a plurality of radon-class features in different directions in the region of interest; and calculating the average value of the radon-class characteristics in a plurality of different directions, and obtaining a radon-class characteristic diagram. In the implementation process, the false recognition rate of finger vein identity authentication on images acquired in a complex image acquisition environment can be effectively reduced by using the radon-class feature map.
Optionally, in the embodiment of the present application, determining the identity information of the identity person to be authenticated according to the multiple similarities includes: and determining the identity information corresponding to the maximum similarity in the multiple similarities as the identity information of the identity personnel to be authenticated. In the implementation process, the identity information corresponding to the maximum similarity in the multiple similarities is determined to be the identity information of the identity personnel to be authenticated, so that the false recognition rate of finger vein identity authentication on the image acquired in the complex image acquisition environment is effectively reduced, and the accuracy rate of finger vein identity authentication is improved under the condition that the safety of the finger vein identity authentication is ensured.
Optionally, in the embodiment of the present application, determining the identity information of the identity person to be authenticated according to the multiple similarities includes: determining a similarity threshold according to the plurality of similarities; comparing the similarity in the plurality of similarities with a similarity threshold value to obtain a comparison result; and determining the identity information of the identity personnel to be authenticated according to the comparison result.
Optionally, in an embodiment of the present application, the plurality of similarities includes: similarity between a plurality of homogeneous feature maps and similarity between a plurality of heterogeneous feature maps; determining a similarity threshold from the plurality of similarities comprises: screening a minimum similarity value from the similarity among the plurality of similar feature images, and screening a maximum similarity value from the similarity among the plurality of heterogeneous feature images; the average of the minimum similarity value and the maximum similarity value is determined as a similarity threshold.
Optionally, in the embodiment of the present application, determining, according to the comparison result, identity information of the identity person to be authenticated includes: if the comparison result shows that the current similarity is larger than the similarity threshold, determining identity information corresponding to the current similarity as the identity information of the identity personnel to be authenticated; if the comparison result is that the current similarity is smaller than the similarity threshold, comparing the next similarity in the plurality of similarities with the similarity threshold.
Optionally, in an embodiment of the present application, before calculating the similarity between the radon-class feature map and the plurality of feature maps in the feature template library, the method further includes: acquiring a plurality of finger vein sample images; extracting a region of interest of each of a plurality of finger vein sample images to obtain a plurality of regions of interest; extracting a radon-class feature map of each of a plurality of regions of interest to obtain a plurality of radon-class feature maps; a plurality of radon-class feature maps are stored to a feature template library. In the implementation process, the plurality of radon-class feature images are stored in the feature template library, so that the speed of acquiring the class feature images from the feature template library and determining the final result of the identity information of the identity personnel to be authenticated after comparison is increased.
The embodiment of the application also provides a finger vein identity authentication device, which comprises: the vein image acquisition module is used for acquiring a finger vein image of the identity personnel to be authenticated; the interest region extraction module is used for extracting an interest region in the finger vein image; the radon feature extraction module is used for extracting a radon-class feature map in the region of interest; the similarity value calculation module is used for calculating the similarity between the radon-class feature images and a plurality of feature images in the feature template library to obtain a plurality of similarities; and the identity information determining module is used for determining the identity information of the identity personnel to be authenticated according to the multiple similarities.
Optionally, in an embodiment of the present application, the radon feature extraction module includes: the different direction extraction module is used for extracting radon-class characteristics in a plurality of different directions in the region of interest; and the class feature map obtaining module is used for calculating the average value of the radon-class features in a plurality of different directions to obtain a radon-class feature map.
Optionally, in an embodiment of the present application, the identity information determining module includes: and the second information determining module is used for determining the identity information corresponding to the maximum similarity in the multiple similarities as the identity information of the identity personnel to be authenticated.
Optionally, in an embodiment of the present application, the identity information determining module includes: the similarity threshold determining module is used for determining a similarity threshold according to the multiple similarities; the comparison result obtaining module is used for comparing the similarity in the plurality of similarities with a similarity threshold value to obtain a comparison result; and the information comparison and determination module is used for determining the identity information of the identity personnel to be authenticated according to the comparison result.
Optionally, in an embodiment of the present application, the plurality of similarities includes: similarity between a plurality of homogeneous feature maps and similarity between a plurality of heterogeneous feature maps; a similarity threshold determination module comprising: the similarity maximum value screening module is used for screening a similarity minimum value from the similarity among the plurality of similar feature images and screening a similarity maximum value from the similarity among the plurality of heterogeneous feature images; and the average value determining threshold module is used for determining the average value of the minimum similarity value and the maximum similarity value as a similarity threshold.
Optionally, in an embodiment of the present application, the information comparison determining module includes: the first information determining module is used for determining identity information corresponding to the current similarity as the identity information of the identity personnel to be authenticated if the comparison result shows that the current similarity is larger than a similarity threshold value; and the similarity value comparison module is used for comparing the next similarity in the plurality of similarities with the similarity threshold value if the comparison result is that the current similarity is smaller than the similarity threshold value.
Optionally, in an embodiment of the present application, the finger vein authentication device further includes: the sample image acquisition module is used for acquiring a plurality of finger vein sample images; the device comprises a region of interest obtaining module, a processing module and a processing module, wherein the region of interest obtaining module is used for extracting a region of interest of each finger vein sample image in a plurality of finger vein sample images to obtain a plurality of regions of interest; the device comprises a radon feature obtaining module, a radon feature extraction module and a radon feature extraction module, wherein the radon feature obtaining module is used for extracting a radon-class feature map of each region of interest in a plurality of regions of interest to obtain a plurality of radon-class feature maps; and the radon feature storage module is used for storing the plurality of radon-class feature graphs into a feature template library.
The embodiment of the application also provides electronic equipment, which comprises: a processor and a memory storing machine-readable instructions executable by the processor to perform the method as described above when executed by the processor.
The embodiments of the present application also provide a storage medium having stored thereon a computer program which, when executed by a processor, performs a method as described above.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and should not be considered as limiting the scope, and other related drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a finger vein identity authentication method according to an embodiment of the present application;
fig. 2 is a schematic diagram of an extraction process of a region of interest according to an embodiment of the present application;
FIG. 3 shows an alternative extraction schematic of the radon-like feature;
fig. 4 is a schematic structural diagram of a finger vein authentication device according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application.
Before introducing the finger vein identity authentication method provided by the embodiment of the application, some concepts related in the embodiment of the application are introduced:
the Radon Transform (Radon Transform), also known as Radon Transform, is an integration Transform that integrates a function f (x, y) defined in a two-dimensional plane along any straight line in the plane.
The sliding window method is to set a window with a fixed height, the width is the image width, slide upwards from the bottom, stop sliding to a certain height, count the sum of pixel values in the current window in the sliding process, and record the image line index corresponding to the central height of the sliding window when the sum of pixel values is the maximum value.
A Charge-Coupled Device (CCD) is a detecting element that uses Charge quantity to represent signal size and uses coupling mode to transmit signal; CCD is widely used in digital photography, astronomy, especially optical telemetry and high-speed photography; the probe element in the CCD refers to a photosensitive unit in a photosensitive element in a camera lens, and corresponds to a pixel of the CCD for obtaining an image.
A server refers to a device that provides computing services over a network, such as: an x86 server and a non-x 86 server, the non-x 86 server comprising: mainframe, minicomputer, and UNIX servers.
It should be noted that, the finger vein authentication method provided by the embodiment of the present application may be executed by an electronic device, where the electronic device refers to a device terminal having a function of executing a computer program or the server described above, and the device terminal is for example: smart phones, personal computers (personal computer, PCs), tablet computers, personal digital assistants (personal digital assistant, PDAs), mobile internet appliances (mobile Internet device, MIDs), network switches or network routers, and the like.
Before introducing the finger vein identity authentication method provided by the embodiment of the present application, application scenarios applicable to the finger vein identity authentication method are introduced, where the application scenarios include, but are not limited to: the finger vein identity authentication method is used for carrying out identity authentication, identity recognition and the like according to the finger vein image, and the function of a security system or an access control system is enhanced.
Please refer to fig. 1, which is a schematic flow chart of a finger vein authentication method according to an embodiment of the present application; the main idea of the finger vein identity authentication method is that the finger vein identity authentication is carried out by extracting a region of interest in a finger vein image, extracting a radon-class feature map in the region of interest, and then using the radon-class feature map. Because the radon-class feature map allows the statistical information of the spatially distributed images (spatially distributed image) to be aggregated into compact feature descriptors (feature descriptors) and is insensitive to information such as image background, image noise, finger displacement, rotation angle and the like, the use of the radon-class feature map can effectively reduce the false recognition rate of finger vein identity authentication on images acquired in a complex image acquisition environment. The finger vein identity authentication method can comprise the following steps:
step S110: and acquiring a finger vein image of the identity personnel to be authenticated.
The method for acquiring the image of the middle finger vein in the step S110 includes: the first acquisition mode is to shoot a target object by using a terminal device such as an infrared camera or a Charge Coupled Device (CCD) camera, and acquire a finger vein image of a finger of an identity person to be authenticated; then the terminal equipment sends the finger vein image to the electronic equipment, then the electronic equipment receives the finger vein image sent by the terminal equipment, and the electronic equipment can store the finger vein image into a file system, a database or a mobile storage device; in the second acquisition mode, a finger vein image stored in advance is acquired, specifically for example: acquiring a finger vein image from a file system, acquiring a finger vein image from a database, or acquiring a finger vein image from a mobile storage device; in a third acquisition mode, a finger vein image is acquired on the internet by using software such as a browser, or the finger vein image is acquired by accessing the internet by using other application programs.
After step S110, step S120 is performed: a region of interest in the finger vein image is extracted.
A region of interest (Region Of Interest, ROI), which refers to a region capable of reflecting an identity feature; that is, the features extracted by using the region of interest can be used for identity authentication or identity recognition, and the main function of ROI extraction is to extract the region capable of reflecting the identity features and remove the irrelevant region so as to prevent the interference on the accuracy of identity authentication. Therefore, the specific content of the ROI is different depending on the application scene, and any region of interest capable of identity authentication or identity recognition may be used, and the ROI is not specifically limited to a specific region of the finger vein image or is in a specific shape.
Please refer to fig. 2, which illustrates a schematic diagram of an extraction process of a region of interest according to an embodiment of the present application; the above-mentioned implementation of step S120 is very various, including but not limited to the following:
a first embodiment, which uses a finger vein ROI positioning method based on a 3 sigma criterion dynamic threshold strategy to extract a region of interest in a finger vein image, specifically for example: performing preliminary filtering and image smoothing on an original input finger vein image to obtain a smooth image, and removing a frame part without finger veins in the smooth image, namely cutting out a region frame without fingers to obtain a trimming image; then, edge detection is carried out on the edge removed image by using a Kirsch operator (Kirsch operator) to obtain a Kirsch gradient image, and binarization is carried out on the Kirsch gradient image by using mu+2σ to obtain first edge data of a binary image; then binarizing the Kirsch gradient image by using mu+sigma as a threshold value to obtain second edge data of the binary image, and binarizing the Kirsch gradient image by using mu+0.5sigma as the threshold value to obtain third edge data of the binary image; finally, combining the first edge data, the second edge data and the third edge data of the binary image to obtain a combined edge data image, interpolating and splicing a front Jing Quxian (namely a white curve) in the combined edge data image to obtain a complete finger edge image, and then intercepting an interested region from the complete finger edge image along the edge; wherein μ refers to the average value of normally distributed pixels in the Kirsch gradient image, and σ refers to the standard deviation of normally distributed pixels in the Kirsch gradient image.
In a second embodiment, a sliding window method is used to extract a region of interest in a finger vein image, where the embodiment specifically includes: calculating an internal tangent line of the edge of the finger area corresponding to the finger vein image to be processed; intercepting a finger vein image to be processed by using the internal tangent line to obtain an intercepted image; interpolation and normalization are carried out on the intercepted image by using an interpolation algorithm, and an interpolated and normalized image is obtained; a sliding window method is used to extract the region of interest from the interpolated and normalized image, where interpolation algorithms that may be used herein include, but are not limited to: nearest neighbor interpolation, bilinear interpolation, and bicubic interpolation.
After step S120, step S130 is performed: and extracting a radon-class feature map in the region of interest.
Radon-Like Features (RLF), also known as Radon-Like Features, are a feature used in medical image processing and analysis, and the basic idea of RLF derives from Radon transformation (Radon Transform).
Fig. 3 shows an alternative extraction schematic of the radon-class feature, and the implementation of step S130 may include:
step S131: a plurality of segmentation points (denoted Knot) and an extraction function (i.e. T-function) are set.
The plurality of segment points (indicated as Knot) in step S131 are provided in the following manner: firstly, as shown in a sub-graph (a) in fig. 3, an image corresponding to a region of interest in a finger vein image is obtained, and then an average curvature (mean curvature) of the image corresponding to the region of interest is calculated according to an existing method to obtain an average curvature graph, wherein the average curvature graph is shown in a sub-graph (b) in fig. 3; then, the edge of the graph is detected by using a canny operator to obtain a canny edge detection result image, wherein the canny edge detection result image can be represented by E (x, y), the canny edge detection result image is shown as a (c) sub-graph in fig. 3, and an intersection point of E (x, y) and a straight line l is determined as the segmentation point, so that a plurality of segmentation points can be obtained, namely a knot can be obtained.
The manner of setting the extraction function (i.e., T function) in step S131 is as follows: the T function may be set to
Wherein, i (x, y) is the input image corresponding to the region of interest, g (x, y) is the normalization result of the input region of interest image I (x, y), I x Is the gradient (or difference) of the region of interest image I (X, y) in the X direction, I y Is the gradient (or difference) of the region of interest image I (x, Y) in the Y direction, I xx ,I xy ,I yy Is the second order gradient (or second order difference) of the region of interest image I (x, y). It will be appreciated that the actual meaning of the T function described above is that will be [ T ] i ,t i+1 ]The gray value of the pixel point in the middle is set as t i ,t i+1 ]The average value of gray values of all pixel points in the pixel array.
Step S132: a plurality of segmentation points (denoted Knot) and an extraction function (i.e. a T-function) are used to extract a plurality of different-directional radon-like features in a corresponding image of the region of interest.
The embodiment of step S132 described above is, for example: firstly taking 8 different directions of straight line l directions of radian 0, pi/4, pi/2, 3 pi/4, pi, 5 pi/4, 3 pi/2 and 7 pi/4, namely 0 degree, 45 degrees, 90 degrees, 135 degrees, 180 degrees, 225 degrees, 270 degrees and 315 degrees respectively, then using a plurality of segmentation points (expressed as Knot) to carry out segmentation processing on the image I (x, y) of the region of interest along the straight lines (expressed as l) of the 8 different directions, and each segment after segmentation can be calculated through a predefined extraction function (namely T function), and outputting the calculation result of the extraction function as Radon-like characteristics to obtain the Radon-like characteristics of 8 directions, wherein the Radon-like characteristics of the 8 directions are shown as a sub graph in (d) in fig. 3. It will be appreciated that where the line is segmented is determined by a number of segmentation points (denoted Knot), and how each segment after segmentation computes the features is determined by a T-function.
The extraction process of the radon-class feature map described above is expressed using the formula: assume that a straight line is expressed as a parameter formWherein t represents a parameter, t.epsilon.a, b]A and b represent the lower and upper boundaries of a straight line, respectively, x represents the abscissa of the straight line, y represents the ordinate of the straight line, and l (t) represents the parametric equation of the straight line. The division of the straight line l into n segments can be represented by dividing the interval of the value of the parameter t into n segments, namely by the formula [ t ] 0 ＝a,t 1 ],[t 1 ,t 2 ],…,[t n-1 ,t n ＝b]For any one line segment [ t ] i ,t i+1 ]The extraction formula of the radon-class features is that i=0, …, n-1:
ψ(p,l,t i ,t i+1 )[I(x,y)]＝T(I(x,y),l(t)),t∈[t i ,t i+1 ]；
wherein, ψ (p, l, t) i ,t i+1 )[I(x,y)]Representing a radon-class feature, t 0 ,…,t n For n+1 segmentation points (i.e., knot) on the straight line l, T represents a parameter, l (T) represents a parameter equation of the straight line, I (x, y) is an input image corresponding to the region of interest, and T (I (x, y), l (T)) represents a function of extracting a radon-class feature map in the image corresponding to the region of interest according to the parameter equation of the straight line.
It will be appreciated that the main function of the above line is to determine the specific direction in which the radon-like feature needs to be extracted, while the above Knot may be understood as a plurality of segmentation points on the line, and the function of the Knot (i.e. the plurality of segmentation points) is to enable the feature extraction process to maintain diversity in the same linear direction, where diversity is specifically for example: the image may be divided by a straight line and a plurality of segmentation points on the straight line into a background at the image boundary (e.g., the background at the upper and lower boundaries in the edge detection result image in fig. 3) and a foreground at the image center (e.g., the foreground at the vertical center in the edge detection result image in fig. 3), the background at the image boundary generally needs to be suppressed (i.e., the radon-class features are not extracted as much as possible from the background at the image boundary), and the foreground at the image center needs to be enhanced (i.e., the radon-class features are extracted as much as possible from the foreground at the image center).
Step S133: and calculating the average value of the radon-class characteristics in a plurality of different directions, and obtaining a radon-class characteristic diagram.
The embodiment of step S133 described above is, for example: the average value of the Radon-like features in 8 directions is calculated, and the obtained result is the average Radon-like feature of the image I (x, y) corresponding to the region of interest, namely a Radon-like feature map shown in (e) sub-graph in FIG. 3.
After step S130, step S140 is performed: and calculating the similarity between the radon-class feature map and a plurality of feature maps in the feature template library to obtain a plurality of similarities.
Optionally, before calculating the similarity using the feature map in the feature template library, the feature map needs to be stored in the feature template library, and this embodiment may include: acquiring a plurality of finger vein sample images, extracting an interested region of each finger vein sample image in the plurality of finger vein sample images, acquiring a plurality of interested regions, extracting a radon-class feature map of each interested region in the plurality of interested regions, acquiring a plurality of radon-class feature maps, and finally storing the plurality of radon-class feature maps into a feature template library. It is to be understood that the above-described process of obtaining the plurality of radon-class feature maps is similar to the above-described embodiments of step S110 to step S130, and thus, the description of the embodiments and the implementation principle of obtaining the plurality of radon-class feature maps will not be described here, and reference may be made to the descriptions of step S110 to step S130, if it is unclear.
The embodiment of step S140 described above is, for example: calculating a similarity R between the feature image V (x, y) extracted from the region of interest image I (x, y) and each template feature image R (x, y) in the feature template library m A plurality of similarities can be obtained; wherein the plurality of similarities comprises: similarity between a plurality of homogeneous feature maps and similarity between a plurality of heterogeneous feature maps. The specific calculation process of the similarity is as follows: first, the size of the feature map V (x, y) extracted from the region-of-interest image is calculated as (h-2 c h -1,w-2c w -1) central region similarity of the same size of each image block to each template feature map R (x, y) in the feature template library. The specific calculation formula of the similarity of the central area is as follows:
wherein,(h-2c h -1,w-2c w -1) is the size of the dimension in the feature map V (x, y) extracted from the region of interest image, c w ＝40，c h =40, V (x, y) is a feature map extracted from the region of interest image I (x, y), R (x, y) is a template feature map in the feature template library, and the sizes of R (x, y) and V (x, y) are both w×h.
Reuse formulaCalculate N m Maximum value of (s, t), finally, using the formulaPerforming normalization operation to obtain the similarity of the central region; wherein R is m The value range of (2) is [0,0.5 ]]V (x, y) is a feature map extracted from the region of interest image I (x, y), and R (x, y) is a template feature map in the feature template library.
After step S140, step S150 is performed: and determining the identity information of the identity personnel to be authenticated according to the multiple similarities.
The above-mentioned implementation of step S150 is various, including but not limited to the following:
in the first embodiment, identity information corresponding to the maximum similarity is directly determined as the identity information of the identity personnel to be authenticated, and the embodiment specifically includes: and determining the identity information corresponding to the maximum similarity in the multiple similarities as the identity information of the identity personnel to be authenticated.
In a second embodiment, determining a similarity threshold from a plurality of similarities, and determining identity information according to the similarity threshold, the embodiment may include:
step S151: a similarity threshold is determined from the plurality of similarities.
The embodiment of step S151 includes: screening a minimum similarity value from the similarity among the plurality of similar feature images, and screening a maximum similarity value from the similarity among the plurality of heterogeneous feature images; the average of the minimum similarity value and the maximum similarity value is determined as a similarity threshold. The specific process of determining the similarity threshold is as follows: assume that a plurality of feature graphs in a feature template library are denoted as I 1 ,I 2 ,…,I n Each radon-class feature map I i And I 1 ,I 2 ,…,I n The similarity between is expressed asWherein i=1, …, n; j=1, …, i-1, i+1, … n; respectively calculating each radon-class characteristic diagram I i Minimum similarity to a homogeneous feature map (also referred to as homogeneous sample or homogeneous feature map), where the minimum similarity can be expressed as +.>Calculating each radon-class feature map I i The maximum value of similarity with a heterogeneous feature map (also referred to as a heterogeneous sample or a heterogeneous feature map), where the maximum value of similarity may representIs->And then find outFinally according to the formula->Calculating a similarity threshold; wherein τ is a similarity threshold, +.>For each radon-class feature map, the similarity between the radon-class feature map and the class feature map is the minimum,/>And (5) maximizing the similarity between each radon-class feature map and the heterogeneous feature map.
Step S152: and comparing the similarity in the plurality of similarities with a similarity threshold value to obtain a comparison result.
Step S153: and determining the identity information of the identity personnel to be authenticated according to the comparison result.
The embodiments of the above steps S152 to S153 are, for example: comparing the current similarity of the plurality of similarities with a similarity threshold, and judging whether the current similarity of the plurality of similarities is larger than the similarity threshold, namely judging R m >Whether the condition of τ is satisfied. If the comparison result shows that the current similarity is larger than the similarity threshold, determining identity information corresponding to the current similarity as the identity information of the identity personnel to be authenticated; if the comparison result is that the current similarity is smaller than the similarity threshold, comparing the next similarity in the plurality of similarities with the similarity threshold.
In the implementation process, extracting a region of interest in the finger vein image, extracting a radon-class feature map in the region of interest, and then performing finger vein identity authentication by using the radon-class feature map; because the radon-class feature map allows the statistical information of the spatially distributed images (spatially distributed image) to be aggregated into compact feature descriptors (feature descriptors) and is insensitive to information such as image background, image noise, finger displacement, rotation angle and the like, the use of the radon-class feature map can effectively reduce the false recognition rate of finger vein identity authentication on images acquired in a complex image acquisition environment.
Please refer to fig. 4, which illustrates a schematic structure diagram of a finger vein authentication device according to an embodiment of the present application; the embodiment of the application provides a finger vein identity authentication device 200, which comprises:
the vein image acquisition module 210 is configured to acquire a finger vein image of an identity person to be authenticated.
The region of interest extraction module 220 is configured to extract a region of interest in the finger vein image.
A radon feature extraction module 230, configured to extract a radon-class feature map in the region of interest.
The similarity value calculating module 240 is configured to calculate the similarity between the radon-class feature map and a plurality of feature maps in the feature template library, so as to obtain a plurality of similarities.
The identity information determining module 250 is configured to determine identity information of the identity person to be authenticated according to the multiple similarities.
Optionally, in an embodiment of the present application, the radon feature extraction module includes:
and the different direction extraction module is used for extracting the radon-class characteristics in a plurality of different directions in the region of interest.
And the class feature map obtaining module is used for calculating the average value of the radon-class features in a plurality of different directions to obtain a radon-class feature map.
Optionally, in an embodiment of the present application, the identity information determining module includes:
and the similarity threshold determining module is used for determining a similarity threshold according to the multiple similarities.
And the comparison result obtaining module is used for comparing the similarity in the plurality of similarities with a similarity threshold value to obtain a comparison result.
And the information comparison and determination module is used for determining the identity information of the identity personnel to be authenticated according to the comparison result.
Optionally, in an embodiment of the present application, the plurality of similarities includes: similarity between a plurality of homogeneous feature maps and similarity between a plurality of heterogeneous feature maps; a similarity threshold determination module comprising:
the similarity maximum value screening module is used for screening a similarity minimum value from the similarity among the plurality of similar feature images and screening a similarity maximum value from the similarity among the plurality of heterogeneous feature images.
And the average value determining threshold module is used for determining the average value of the minimum similarity value and the maximum similarity value as a similarity threshold.
Optionally, in an embodiment of the present application, the information comparison determining module includes:
and the first information determining module is used for determining the identity information corresponding to the current similarity as the identity information of the identity personnel to be authenticated if the comparison result is that the current similarity is larger than the similarity threshold value.
And the similarity value comparison module is used for comparing the next similarity in the plurality of similarities with the similarity threshold value if the comparison result is that the current similarity is smaller than the similarity threshold value.
Optionally, in an embodiment of the present application, the identity information determining module further includes:
and the second information determining module is used for determining the identity information corresponding to the maximum similarity in the multiple similarities as the identity information of the identity personnel to be authenticated.
Optionally, in an embodiment of the present application, the finger vein authentication device further includes:
and the sample image acquisition module is used for acquiring a plurality of finger vein sample images.
The region of interest obtaining module is used for extracting the region of interest of each finger vein sample image in the plurality of finger vein sample images to obtain a plurality of regions of interest.
And the radon characteristic obtaining module is used for extracting a radon-class characteristic diagram of each region of interest in the multiple regions of interest to obtain multiple radon-class characteristic diagrams.
And the radon feature storage module is used for storing the plurality of radon-class feature graphs into a feature template library.
It should be understood that, the apparatus corresponds to the above finger vein authentication method embodiment, and is capable of executing the steps involved in the above method embodiment, and specific functions of the apparatus may be referred to the above description, and detailed descriptions are omitted herein as appropriate to avoid repetition. The device includes at least one software functional module that can be stored in memory in the form of software or firmware (firmware) or cured in an Operating System (OS) of the device.
Please refer to fig. 5, which illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application. An electronic device 300 provided in an embodiment of the present application includes: a processor 310 and a memory 320, the memory 320 storing machine-readable instructions executable by the processor 310, which when executed by the processor 310 perform the method as described above.
The embodiment of the present application also provides a storage medium 330, on which storage medium 330 a computer program is stored which, when executed by a processor 310, performs a method as above.
Wherein the storage medium 330 may be implemented by any type or combination of volatile or non-volatile Memory devices, such as a static random access Memory (Static Random Access Memory, SRAM), an electrically erasable Programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), an erasable Programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), a Programmable Read-Only Memory (PROM), a Read-Only Memory (ROM), a magnetic Memory, a flash Memory, a magnetic disk, or an optical disk.
In the embodiments of the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus embodiments described above are merely illustrative, for example, of the flowcharts and block diagrams in the figures that illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules of the embodiments of the present application may be integrated together to form a single part, or the modules may exist separately, or two or more modules may be integrated to form a single part.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
The foregoing description is merely an optional implementation of the embodiment of the present application, but the scope of the embodiment of the present application is not limited thereto, and any person skilled in the art may easily think about changes or substitutions within the technical scope of the embodiment of the present application, and the changes or substitutions are covered by the scope of the embodiment of the present application.
Claims (8)
1. A finger vein authentication method, comprising:
acquiring a finger vein image of an identity person to be authenticated;
extracting a region of interest in the finger vein image;
extracting a radon-class feature map in the region of interest;
calculating the similarity between the radon-class feature images and a plurality of feature images in a feature template library to obtain a plurality of similarities;
determining identity information of the identity personnel to be authenticated according to the plurality of similarities;
the step of determining the identity information of the identity personnel to be authenticated according to the plurality of similarities comprises the following steps: determining a similarity threshold according to the plurality of similarities; comparing the similarity in the plurality of similarities with the similarity threshold to obtain a comparison result; determining the identity information of the identity personnel to be authenticated according to the comparison result;
the plurality of similarities includes: similarity between a plurality of homogeneous feature maps and similarity between a plurality of heterogeneous feature maps; the determining a similarity threshold according to the plurality of similarities comprises: screening out a minimum similarity value from the similarity among the plurality of similar feature images, and screening out a maximum similarity value from the similarity among the plurality of heterogeneous feature images; according to the formulaAnd formula->Determining an average value of the minimum similarity value and the maximum similarity value as the similarity threshold; wherein, τ for the similarity threshold, +_>For the minimum similarity between the radon-class feature map and the class feature map, ++>Is the maximum similarity between the radon-class feature map and the heterogeneous feature map.
2. The method of claim 1, wherein the extracting a radon-class feature map in the region of interest comprises:
extracting a plurality of radon-like features in different directions in the region of interest;
and calculating the average value of the radon-class characteristics in the plurality of different directions, and obtaining the radon-class characteristic diagram.
3. The method of claim 1, wherein the determining the identity information of the identity person to be authenticated according to the plurality of similarities comprises:
and determining the identity information corresponding to the maximum similarity in the multiple similarities as the identity information of the identity personnel to be authenticated.
4. The method according to claim 1, wherein the determining the identity information of the identity person to be authenticated according to the comparison result includes:
if the comparison result shows that the current similarity is larger than the similarity threshold, determining identity information corresponding to the current similarity as the identity information of the identity personnel to be authenticated;
and if the comparison result is that the current similarity is smaller than the similarity threshold value, comparing the next similarity in the plurality of similarities with the similarity threshold value.
5. The method of any one of claims 1-4, further comprising, prior to said computing similarity of said radon-class feature map to a plurality of feature maps in a feature template library:
acquiring a plurality of finger vein sample images;
extracting a region of interest of each of the plurality of finger vein sample images to obtain a plurality of regions of interest;
extracting a radon-class feature map of each region of interest in the plurality of regions of interest to obtain a plurality of radon-class feature maps;
storing the plurality of radon-class feature maps to the feature template library.
6. A finger vein authentication device, comprising:
the vein image acquisition module is used for acquiring a finger vein image of the identity personnel to be authenticated;
the interest region extraction module is used for extracting an interest region in the finger vein image;
the radon feature extraction module is used for extracting a radon-class feature map in the region of interest;
the similarity value calculation module is used for calculating the similarity between the radon-class feature images and a plurality of feature images in the feature template library to obtain a plurality of similarity;
the identity information determining module is used for determining the identity information of the identity personnel to be authenticated according to the plurality of similarities;
the step of determining the identity information of the identity personnel to be authenticated according to the plurality of similarities comprises the following steps: determining a similarity threshold according to the plurality of similarities; comparing the similarity in the plurality of similarities with the similarity threshold to obtain a comparison result; determining the identity information of the identity personnel to be authenticated according to the comparison result;
the plurality of similarities includes: similarity between a plurality of homogeneous feature maps and similarity between a plurality of heterogeneous feature maps; the determining a similarity threshold according to the plurality of similarities comprises: screening out a minimum similarity value from the similarity among the plurality of similar feature images, and screening out a maximum similarity value from the similarity among the plurality of heterogeneous feature images; according to the formulaAnd formula->Sum the similarity minimum valueThe average value of the similarity maximum values is determined to be the similarity threshold value; wherein, τ for the similarity threshold, +_>For the minimum similarity between the radon-class feature map and the class feature map, ++>Is the maximum similarity between the radon-class feature map and the heterogeneous feature map.
7. An electronic device, comprising: a processor and a memory storing machine-readable instructions executable by the processor to perform the method of any one of claims 1 to 5 when executed by the processor.
8. A storage medium having stored thereon a computer program which, when executed by a processor, performs the method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110053733.1A CN112711748B (en) | 2021-01-15 | 2021-01-15 | Finger vein identity authentication method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110053733.1A CN112711748B (en) | 2021-01-15 | 2021-01-15 | Finger vein identity authentication method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112711748A CN112711748A (en) | 2021-04-27 |
| CN112711748B true CN112711748B (en) | 2023-12-05 |
Family
ID=75549102
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110053733.1A Active CN112711748B (en) | 2021-01-15 | 2021-01-15 | Finger vein identity authentication method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112711748B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104573633A (en) * | 2014-12-15 | 2015-04-29 | 广东智冠信息技术股份有限公司 | Matching and identifying method for bionic textures and linear textures of finger veins |
| CN104615634A (en) * | 2014-11-10 | 2015-05-13 | 广东智冠信息技术股份有限公司 | Direction feature based palm vein guiding quick retrieval method |
| CN110717372A (en) * | 2019-08-13 | 2020-01-21 | 平安科技（深圳）有限公司 | Identity verification method and device based on finger vein recognition |
-
2021
- 2021-01-15 CN CN202110053733.1A patent/CN112711748B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104615634A (en) * | 2014-11-10 | 2015-05-13 | 广东智冠信息技术股份有限公司 | Direction feature based palm vein guiding quick retrieval method |
| CN104573633A (en) * | 2014-12-15 | 2015-04-29 | 广东智冠信息技术股份有限公司 | Matching and identifying method for bionic textures and linear textures of finger veins |
| CN110717372A (en) * | 2019-08-13 | 2020-01-21 | 平安科技（深圳）有限公司 | Identity verification method and device based on finger vein recognition |
Non-Patent Citations (2)
| Title |
|---|
| Radon-Like Features and their Application to Connectomics;Ritwik Kumar等;《2010IEEE computer society conference on computer vision and pattern recognition-workshops》;20101231;第186-193页 * |
| 基于生物特征信息隐藏与身份认证及其应用研究;王德松;《中国博士学位论文全文数据库》;20121231(第12期);第I138-5页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112711748A (en) | 2021-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10789465B2 (en) | Feature extraction and matching for biometric authentication | |
| CN109753838B (en) | Two-dimensional code identification method, device, computer equipment and storage medium | |
| CN110569721A (en) | Recognition model training method, image recognition method, device, equipment and medium | |
| CN111695410A (en) | Violation reporting method and device, computer equipment and storage medium | |
| CN111626163A (en) | Human face living body detection method and device and computer equipment | |
| CN111882565B (en) | Image binarization method, device, equipment and storage medium | |
| CN113228105B (en) | Image processing method, device and electronic equipment | |
| CN110516731B (en) | Visual odometer feature point detection method and system based on deep learning | |
| CN110765875B (en) | Method, equipment and device for detecting boundary of traffic target | |
| CN116030280A (en) | Template matching method, device, storage medium and equipment | |
| CN108229583A (en) | A kind of method and device of the fast Template Matching based on principal direction Differential Characteristics | |
| CN113344961B (en) | Image background segmentation method, device, computing equipment and storage medium | |
| CN111062927A (en) | Method, system and equipment for detecting image quality of unmanned aerial vehicle | |
| CN111915645B (en) | Image matching method and device, computer equipment and computer readable storage medium | |
| CN112711748B (en) | Finger vein identity authentication method and device, electronic equipment and storage medium | |
| CN117496560B (en) | Fingerprint line identification method and device based on multidimensional vector | |
| CN112784837B (en) | Region of interest extraction method and device, electronic equipment and storage medium | |
| US12125218B2 (en) | Object tracking apparatus and method | |
| CN113239738B (en) | Image blurring detection method and blurring detection device | |
| CN112906495B (en) | Target detection method and device, electronic equipment and storage medium | |
| CN112085683B (en) | Depth map credibility detection method in saliency detection | |
| CN115131831A (en) | Fingerprint image segmentation method and device, electronic equipment and storage medium | |
| CN114764839A (en) | Dynamic video generation method and device, readable storage medium and terminal equipment | |
| CN111767751A (en) | Two-dimensional code image identification method and device | |
| CN116363031B (en) | Imaging method, device, equipment and medium based on multidimensional optical information fusion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230915 Address after: 528400, Xueyuan Road, 1, Shiqi District, Guangdong, Zhongshan Applicant after: University OF ELECTRONIC SCIENCE AND TECHNOLOGY OF CHINA, ZHONGSHAN INSTITUTE Applicant after: Productivity Promotion Center of Xiaolan Town, Zhongshan City Address before: 528400, Xueyuan Road, 1, Shiqi District, Guangdong, Zhongshan Applicant before: University OF ELECTRONIC SCIENCE AND TECHNOLOGY OF CHINA, ZHONGSHAN INSTITUTE |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |